diff --git a/src/axolotl/utils/models.py b/src/axolotl/utils/models.py
index 8d24524a2..35005bfce 100644
--- a/src/axolotl/utils/models.py
+++ b/src/axolotl/utils/models.py
@@ -96,12 +96,6 @@ def check_model_config(cfg: DictDefault, model_config: Union[AutoConfig, DictDef
             "Please make sure to point to a GPTQ model."
         )
 
-    if not cfg.gptq and quant_config_exists and not cfg.load_in_4bit:
-        raise ValueError(
-            "model_config.quantization_config is set but `gptq` flag is not. "
-            "Please use the `gptq` flag to train quantized model or point to a non-quantized model."
-        )
-
     lora_modules_to_save = get_linear_embedding_layers(model_config.model_type)
     if (
         cfg.adapter